{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T18:13:26Z","timestamp":1775326406994,"version":"3.50.1"},"reference-count":56,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100001602","name":"Science Foundation Ireland","doi-asserted-by":"publisher","award":["14\/IA\/2474"],"award-info":[{"award-number":["14\/IA\/2474"]}],"id":[{"id":"10.13039\/501100001602","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/access.2019.2959905","type":"journal-article","created":{"date-parts":[[2019,12,17]],"date-time":"2019-12-17T00:34:11Z","timestamp":1576542851000},"page":"7861-7876","source":"Crossref","is-referenced-by-count":12,"title":["A Hierarchical Data-Partitioning Algorithm for Performance Optimization of Data-Parallel Applications on Heterogeneous Multi-Accelerator NUMA Nodes"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4070-7468","authenticated-orcid":false,"given":"Hamidreza","family":"Khaleghzadeh","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9181-3290","authenticated-orcid":false,"given":"Ravi Reddy","family":"Manumachu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9460-3897","authenticated-orcid":false,"given":"Alexey","family":"Lastovetsky","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1006\/jpdc.2000.1686"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/71.963416"},{"key":"ref33","year":"2019","journal-title":"The OmpSs Programming Model"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1142\/S0129626411000151"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICACCI.2016.7732032"},{"key":"ref30","first-page":"1","article-title":"GHOST: Building blocks for high performance sparse linear algebra on heterogeneous systems","volume":"45","author":"kreutzer","year":"2016","journal-title":"Int J Parallel Program"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1093\/comjnl\/40.6.356"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s11265-015-1051-z"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/1735688.1735702"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2009.5306797"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ISICIR.2014.7029447"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ARES.2013.94"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICPADS.2013.71"},{"key":"ref2","year":"2018","journal-title":"Green500 list for November 2018"},{"key":"ref1","year":"2018","journal-title":"TOP500 List-November 2018"},{"key":"ref20","author":"corporation","year":"2018","journal-title":"Intel Math Kernel Library-Intel MKL FFT"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1117\/12.681085"},{"key":"ref21","year":"2018","journal-title":"Optimized FFT Routines for NVIDIA Graphics Processors"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/1723112.1723134"},{"key":"ref23","article-title":"QP: A heterogeneous multi-accelerator cluster","author":"showerman","year":"2009","journal-title":"Proc 10th LCI Int Conf High-Perform Clustered Comput"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1155\/2012\/241439"},{"key":"ref25","first-page":"73","article-title":"A parallel computing system with specialized coprocessors for cryptanalytic algorithms","author":"kastl","year":"2010","journal-title":"Proc Sicherheit"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ISPA.2012.101"},{"key":"ref51","first-page":"693","article-title":"Transparent application acceleration by intelligent scheduling of shared library calls on heterogeneous systems","author":"cola\u00e7o","year":"2013","journal-title":"Parallel Processing and Applied Mathematics"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/MASCOTS.2015.11"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1016\/j.suscom.2014.08.003"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-32820-6_49"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/SSDM.2003.1214983"},{"key":"ref52","first-page":"203","article-title":"Heterogeneous sparse matrix computations on hybrid GPU\/CPU platforms","author":"cardellini","year":"2013","journal-title":"Proc PARCO"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2016.2608824"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2879228"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/12.956091"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2014.2375202"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2018.2827055"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2015.06.006"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/2967938.2967961"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/1362622.1362688"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.4958"},{"key":"ref18","author":"corporation","year":"2018","journal-title":"Intel Intel Math Kernel Library"},{"key":"ref19","year":"2017","journal-title":"CUDA Toolkit Documentation"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.parco.2009.12.005"},{"key":"ref3","year":"2016","journal-title":"CUBLAS-XT Multi-GPU Version of CUBLAS Library Supporting Out-of-Core Routines"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.parco.2007.06.001"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-017-2141-4"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-29737-3_50"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1142\/S0129626411000163"},{"key":"ref49","first-page":"417","article-title":"Efficient computation of Galois field expressions on hybrid CPU-GPU platforms","volume":"26","author":"radmanovi?","year":"2016","journal-title":"J Multiple-Valued Logic Soft Comput"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2016.2599527"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1177\/1094342006074864"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1155\/2005\/964902"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2015.08.002"},{"key":"ref47","first-page":"202","article-title":"High-performance computing on heterogeneous systems: Database queries on CPU and GPU","author":"ili?","year":"2010","journal-title":"High Performance Scientific Computing with Special Emphasis on Current Capabilities and Future Perspectives"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/1513895.1513901"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-73940-1_27"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2004.1303051"},{"key":"ref43","first-page":"457","article-title":"Towards efficient decomposition and parallelization of MPDATA on hybrid CPU-GPU cluster","author":"wyrzykowski","year":"2013","journal-title":"Proc Int Conf Large-Scale Sci Comput"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8948470\/08933138.pdf?arnumber=8933138","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,17]],"date-time":"2021-12-17T19:50:17Z","timestamp":1639770617000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8933138\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":56,"URL":"https:\/\/doi.org\/10.1109\/access.2019.2959905","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}